Error-backpropagation in temporally encoded networks of spiking neurons

For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional errorbackpropagation. With this algorithm, we demonstrate how networks of spiking neurons with biologically reasonable action potentials can perform complex non-linear classi

• Type: Journal
• Year: 2002
• Where: IJON
• Authors: Sander M. Bohte, Joost N. Kok, Johannes A. La Poutré
• Keywords: Classical Xor Problem, IJON 2002, Neurons, XOR Problem